| { |
| "best_metric": 0.8816773017319963, |
| "best_model_checkpoint": "ft/checkpoint-2046", |
| "epoch": 7.0, |
| "eval_steps": 500, |
| "global_step": 2387, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_f1": 0.25525268677252616, |
| "eval_loss": 0.0030135156121104956, |
| "eval_precision": 0.42857142857142855, |
| "eval_recall": 0.25118934348239774, |
| "eval_runtime": 46.7461, |
| "eval_samples_per_second": 29.136, |
| "eval_steps_per_second": 1.84, |
| "step": 341 |
| }, |
| { |
| "epoch": 1.47, |
| "learning_rate": 1.8973984286913584e-05, |
| "loss": 0.0524, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1": 0.7398991743990649, |
| "eval_loss": 0.0016016679583117366, |
| "eval_precision": 0.7088262056414922, |
| "eval_recall": 0.7411988582302569, |
| "eval_runtime": 46.8135, |
| "eval_samples_per_second": 29.094, |
| "eval_steps_per_second": 1.837, |
| "step": 682 |
| }, |
| { |
| "epoch": 2.93, |
| "learning_rate": 1.607725459161122e-05, |
| "loss": 0.0014, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_f1": 0.868271080619986, |
| "eval_loss": 0.0015651908470317721, |
| "eval_precision": 0.7221350078492935, |
| "eval_recall": 0.8753568030447193, |
| "eval_runtime": 46.8355, |
| "eval_samples_per_second": 29.081, |
| "eval_steps_per_second": 1.836, |
| "step": 1023 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_f1": 0.7916895679894471, |
| "eval_loss": 0.0016834472771734, |
| "eval_precision": 0.8179133858267716, |
| "eval_recall": 0.7906755470980019, |
| "eval_runtime": 46.5374, |
| "eval_samples_per_second": 29.267, |
| "eval_steps_per_second": 1.848, |
| "step": 1364 |
| }, |
| { |
| "epoch": 4.4, |
| "learning_rate": 1.1913616304731064e-05, |
| "loss": 0.0007, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_f1": 0.8055126791620728, |
| "eval_loss": 0.001440966036170721, |
| "eval_precision": 0.9016042780748663, |
| "eval_recall": 0.80209324452902, |
| "eval_runtime": 46.5939, |
| "eval_samples_per_second": 29.231, |
| "eval_steps_per_second": 1.846, |
| "step": 1705 |
| }, |
| { |
| "epoch": 5.87, |
| "learning_rate": 7.3510516768689765e-06, |
| "loss": 0.0004, |
| "step": 2000 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_f1": 0.8816773017319963, |
| "eval_loss": 0.001409668242558837, |
| "eval_precision": 0.808695652173913, |
| "eval_recall": 0.884871550903901, |
| "eval_runtime": 46.5762, |
| "eval_samples_per_second": 29.242, |
| "eval_steps_per_second": 1.846, |
| "step": 2046 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_f1": 0.8618469193619203, |
| "eval_loss": 0.0015025387983769178, |
| "eval_precision": 0.8571428571428571, |
| "eval_recall": 0.8620361560418649, |
| "eval_runtime": 46.722, |
| "eval_samples_per_second": 29.151, |
| "eval_steps_per_second": 1.841, |
| "step": 2387 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 3410, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "total_flos": 1.3498705156498326e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
